© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 210422
    Prev
    Next
    INDEX
    Explanations

    actively maintained

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_5_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    }];
    1.46
    ಮ
    1.35
    Coordinates
    1.34
    }";
    1.32
     Ад
    1.29
    자
    1.27
    나
    1.27
    LAH
    1.26
    ش
    1.25
    を集
    1.23
    POSITIVE LOGITS
     l
    1.28
     philosophical
    1.22
     refrigerator
    1.21
     performance
    1.16
     professor
    1.16
     police
    1.14
     machine
    1.13
     joystick
    1.12
     caterpillar
    1.12
     computer
    1.11
    Activations Density 0.000%

    No Known Activations